nep-ecm New Economics Papers
on Econometrics
Issue of 2007‒12‒08
fourteen papers chosen by
Sune Karlsson
Orebro University

  1. Count Data Models with Unobserved Heterogeneity: An Empirical Likelihood Approach By Stefan Boes
  2. Hierarchical Markov normal mixture models with applications to financial asset returns By John Geweke; Gianni Amisano
  3. The Zero-Information-Limit-Condition and Spurious Inference in Weakly Identified Models By Charles Nelson; Richard Startz
  4. A new class of distribution-free tests for time series models specification By Miguel A. Delgado; Carlos Velasco
  5. Hierarchical Parametric Models for Social Dilemma Games By Klaus Moeltner; James J. Murphy; John K. Stranlund; Maria Alejandra Velez
  6. "Estimating Stochastic Volatility Models Using Daily Returns and Realized Volatility Simultaneously" By Makoto Takahashi; Yasuhiro Omori; Toshiaki Watanabe
  7. A residual-based cointegration test for near unit root variables By Erik Hjalmarsson; Par Osterholm
  8. Why Bayes Rules: A Note on Bayesian vs. Classical Inference in Regime Switching Models By Dennis Gaertner
  9. Exchange rate volatility, macro announcements and the choice of intraday seasonality filtering method By Laakkonen, Helinä
  11. Identifying the Returns to Lying When the Truth is Unobserved By Yingyao Hu; Arthur Lewbel
  12. Meta-Functional Benefit Transfer for Wetland Valuation: Making the Most of Small Samples By Klaus Moeltner; Richard T. Woodward
  13. Statistical Surveillance of Epidemics: Peak Detection of Influenza in Sweden By Bock, David; Andersson, Eva; Frisén, Marianne
  14. Meta-Regression and Benefit Transfer: Data Space, Model Space, and the Quest for ‘Optimal Scope’ By Klaus Moeltner; Randall S. Rosenberger

  1. By: Stefan Boes (Socioeconomic Institute, University of Zurich)
    Abstract: As previously argued, the correlation between included and omitted regressors generally causes inconsistency of standard estimators for count data models. Using a specific residual function and suitable instruments, a consistent generalized method of moments estimator can be obtained under conditional moment restrictions. This approach is extended here by fully exploiting the model assumptions and thereby improving efficiency of the resulting estimator. Empirical likelihood estimation in particular has favorable properties in this setting compared to the two-step GMM procedure, which is demonstrated in a Monte Carlo experiment. The proposed method is applied to the estimation of a cigarette demand function.
    Keywords: nonparametric likelihood, poisson model, nonlinear instrumental variables, optimal instruments, approximating functions, semiparametric efficiency
    JEL: C14 C25 D12
    Date: 2007–03
  2. By: John Geweke (Corresponding author: Department of Economics , University of Iowa, Iowa City IA 52242, USA.); Gianni Amisano (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.)
    Abstract: With the aim of constructing predictive distributions for daily returns, we introduce a new Markov normal mixture model in which the components are themselves normal mixtures. We derive the restrictions on the autocovariances and linear representation of integer powers of the time series in terms of the number of components in the mixture and the roots of the Markov process. We use the model prior predictive distribution to study its implications for some interesting functions of returns. We apply the model to construct predictive distributions of daily S&P500 returns, dollar-pound returns, and one- and ten-year bonds. We compare the performance of the model with ARCH and stochastic volatility models using predictive likelihoods. The model's performance is about the same as its competitors for the bond returns, better than its competitors for the S&P 500 returns, and much better for the dollar-pound returns. Validation exercises identify some potential improvements. JEL Classification: C53, G12, C11, C14.
    Keywords: Asset returns, Bayesian, forecasting, MCMC, mixture models.
    Date: 2007–11
  3. By: Charles Nelson; Richard Startz
    Date: 2007–05
  4. By: Miguel A. Delgado; Carlos Velasco
    Abstract: The construction of asymptotically distribution free time series model specification tests using as statistics the estimated residual autocorrelations is considered from a general view point. We focus our attention on Box-Pierce type tests based on the sum of squares of a few estimated residual autocorrelations. This type of tests belongs to the class defined by quadratic forms of weighted residual autocorrelations, where weights are suitably transformed resulting in asymptotically distribution free tests. The weights can be optimally chosen to maximize the power function when testing in the direction of local alternatives. The optimal test in this class against MA, AR or Bloomfield alternatives is a Box-Pierce type test based on the sum of squares of a few transformed residual autocorrelations. Such transformations are, in fact, the recursive residuals in the projection of the residual autocorrelations on a certain score function.
    Date: 2007–11
  5. By: Klaus Moeltner (Department of Resource Economics, University of Nevada, Reno); James J. Murphy (Department of Resource Economics & Center for Public Policy and Administration, University of Massachusetts-Amherst); John K. Stranlund (Department of Resource Economics, University of Massachusetts-Amherst); Maria Alejandra Velez (Center for Research on Environmental Decisions, Columbia University)
    Abstract: Economists have to date not been very discriminating in selecting parametric models to analyze experimental data. In this study we propose two parametric estimators tailored to accommodate both the bounded integer outcomes and the latent subject heterogeneity typically observed for Social Dilemma games. The two estimators are the Hierarchical Ordered Probit and the Hierarchical Doubly-Truncated Poisson. We illustrate how both specifications can be implemented in a Bayesian estimation framework, which circumvents estimation hurdles and allows for maximum flexibility in model comparison and model selection. We apply this framework to data from a Common Pool Resource game implemented in rural communities. We find that both estimators capture the essential effects and patterns present in the data. As expected, the truncated count data framework exhibits higher efficiency in estimation and prediction.
    Keywords: Social Dilemma Games; Hierarchical Bayesian Modeling; Ordered Probit; Truncated Poisson; Common Property Resource
    JEL: C11 C24 C93 Q22
    Date: 2007–12
  6. By: Makoto Takahashi (Graduate School of Economics, University of Tokyo); Yasuhiro Omori (Faculty of Economics, University of Tokyo); Toshiaki Watanabe (Institute of Economic Research, Hitotsubashi University)
    Abstract: Realized volatility, which is the sum of squared intraday returns over a certain interval such as a day, has recently attracted the attention of financial economists and econometricians as an accurate measure of the true volatility. In the real market, however, the presence of non-trading hours and market microstructure noise in transaction prices may cause the bias in the realized volatility. On the other hand, daily returns are less subject to the noise and therefore may provide additional information on the true volatility. From this point of view, we propose modeling realized volatility and daily returns simultaneously based on well-known stochastic volatility model. Using intraday data of Tokyo stock price index, we show that this model can estimate realized volatility biases and parameters simultaneously.We take a Bayesian approach and propose an efficient sampling algorithm to implement the Markov chain Monte Carlo method for our simultaneous model. The result of the model comparison between the simultaneous models using both naive and scaled realized volatilities indicates that the effect of non-trading hours is more essential than that of microstructure noise but still the latter has to be considered for better fitting. Our Bayesian approach has an advantage over the conventional two-step correction procedure in that we are able to take the uncertainty in estimation of both biases and parameters into account for the prediction and the evaluation of Value-at-Risk.
    Date: 2007–09
  7. By: Erik Hjalmarsson; Par Osterholm
    Abstract: Methods of inference based on a unit root assumption in the data are typically not robust to even small deviations from this assumption. In this paper, we propose robust procedures for a residual-based test of cointegration when the data are generated by a near unit root process. A Bonferroni method is used to address the uncertainty regarding the exact degree of persistence in the process. We thus provide a method for valid inference in multivariate near unit root processes where standard cointegration tests may be subject to substantial size distortions and standard OLS inference may lead to spurious results. Empirical illustrations are given by: (i) a re-examination of the Fisher hypothesis, and (ii) a test of the validity of the cointegrating relationship between aggregate consumption, asset holdings, and labor income, which has attracted a great deal of attention in the recent finance literature.
    Date: 2007
  8. By: Dennis Gaertner (Socioeconomic Institute, University of Zurich)
    Abstract: By means of a very simple example, this note illustrates the appeal of using Bayesian rather than classical methods to produce inference on hidden states in models of Markovian regime switching.
    Keywords: Bayesian analysis, switching regression, regime changes, nonlinear filtering
    JEL: C11 C22
    Date: 2007–12
  9. By: Laakkonen, Helinä (University of Jyväskylä)
    Abstract: Filtering intraday seasonality in volatility is crucial for using high frequency data in econometric analysis. This paper studies the effects of filtering on statistical inference concerning the impact of news on exchange rate volatility. The properties of different methods are studied using a 5-minute frequency USD/EUR data set and simulated returns. The simulation results suggest that all the methods tend to produce downward-biased estimates of news coefficients, some more than others. The study supports the Flexible Fourier Form method as the best for seasonality filtering.
    Keywords: high-frequency; volatility; macro announcements; seasonality
    JEL: C22 C49 C52 E44
    Date: 2007–11–28
  10. By: Mahmoudvand, Rahim; Hassani, Hossein; Wilson, Rob
    Abstract: In this paper, we obtain bounds for the population coefficient of variation (CV) in Bernoulli, Discrete Uniform, Normal and Exponential distributions. We also show that the sample coefficient of variation (cv) is not an accurate estimator of the population CV in the above indicated distributions. Finally we provide some suggestions based on the Maximum Likelihood Estimation to improve the population CV estimate.
    Keywords: Coefficient of Variation (CV); Estimator; Maximum Likelihood Estimation (MLE).
    JEL: C13 C02 C40 C60
    Date: 2007–09–07
  11. By: Yingyao Hu (Johns Hopkins University); Arthur Lewbel (Boston College)
    Abstract: Consider an observed binary regressor D and an unobserved binary variable B, both of which affect some other variable Y. This paper considers nonparametric identification and estimation of the effect of D on Y, conditioning on B=0. For example, suppose Y is a person's wage, the unobserved B indicates if the person has been to college, and the observed D indicates whether the individual claims to have been to college. This paper then identifies and estimates the difference in average wages between those who falsely claim college experience versus those who tell the truth about not having college. We estimate this average returns to lying to be about 7% to 20%. Nonparametric identification without observing B is obtained either by observing a variable V that is roughly analogous to an instrument for ordinary measurement error, or by imposing restrictions on model error moments.
    Keywords: Binary regressor, misclassification, measurement error, unobserved factor, discrete factor, program evaluation, treatment effects, returns to schooling, wage model.
    JEL: C14 C13 C20 I2
    Date: 2007–11–28
  12. By: Klaus Moeltner (Department of Resource Economics, University of Nevada, Reno); Richard T. Woodward (Department of Agricultural Economics, Texas A&M University)
    Abstract: This study applies functional Benefit Transfer via Meta-Regression Modeling to derive valuation estimates for wetlands in an actual policy setting of proposed groundwater transfers in Eastern Nevada. We illustrate how Bayesian estimation techniques can be used to overcome small sample problems notoriously present in Meta-functional Benefit Transfer. The highlights of our methodology are (i) The hierarchical modeling of heteroskedasticity, (ii) The ability to incorporate additional information via refined priors, and (ii) The derivation of measures of model performance with the corresponding option of model-averaged Benefit Transfer predictions. Our results indicate that economic losses associated with the disappearance of these wetlands can be substantial and that primary valuation studies are warranted.
    Keywords: Bayesian Model Averaging; t-Error Regression Model; Meta-Analysis; Benefit Transfer; Wetland Valuation
    JEL: C11 C15 Q51
    Date: 2007–12
  13. By: Bock, David (Statistical Research Unit, Department of Economics, School of Business, Economics and Law, Göteborg University); Andersson, Eva (Statistical Research Unit, Department of Economics, School of Business, Economics and Law, Göteborg University); Frisén, Marianne (Statistical Research Unit, Department of Economics, School of Business, Economics and Law, Göteborg University)
    Abstract: A statistical surveillance system gives a signal as soon as data give enough evidence of an important event. We consider on-line surveillance systems for detecting changes in influenza incidence. One important feature of the influenza cycle is the start of the influenza season, and another one is the change to a decline (the peak). In this report we discuss statistical methods for on-line peak detection. One motive for doing this is the need for health resource planning. Surveillance systems were adapted for Swedish data on laboratory verified diagnoses of influenza. In Sweden, the parameters of the influenza cycles vary too much from year to year for parametric methods to be useful. We suggest a non-parametric method based on the monotonicity properties of the increase and decline around a peak. A Monte Carlo study indicated that this method has useful stochastic properties. The method was applied to Swedish data on laboratory verified diagnoses of influenza for seven periods.
    Keywords: Disease surveillance; Monitoring; Non-parametric; Order restrictions
    JEL: C10
    Date: 2007–11–28
  14. By: Klaus Moeltner (Department of Resource Economics, University of Nevada, Reno); Randall S. Rosenberger (Department of Forest Resources, Oregon State University)
    Abstract: Meta-functional Benefit Transfer, while conceptually attractive, is often plagued by the paucity of available source studies and related small sample problems. A broadening of scope of the Meta-Regression Model by adding data from “related, yet different” contexts or activities may circumvent these issues, but may not necessarily enhance the efficiency of transfer functions if the different contexts do not share policy-relevant parameters. We illustrate how different combinations of contexts can be interpreted as ‘data spaces’ which can then be explored for the most promising transfer function using Bayesian Model Search techniques. Our results indicate that for some scope-augmented data spaces model-averaged benefit predictions can be more efficient than those flowing from the baseline context and data.
    Keywords: Bayesian Model Averaging; Stochastic Search Variable Selection; Meta-Analysis; Benefit Transfer; Resource Valuation
    JEL: C11 C15 Q51
    Date: 2007–12

This nep-ecm issue is ©2007 by Sune Karlsson. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.